© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40463
    Prev
    Next
    INDEX
    Explanations

    phosphorus, formulas, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yards
    -0.30
     ///<
    -0.27
    Assistant
    -0.27
    æݧ
    -0.25
    Scripts
    -0.24
    åĬĽè¿ĺæĺ¯
    -0.24
    å¹´åĪĿ
    -0.24
    æŃĥ
    -0.24
    yte
    -0.24
    eking
    -0.24
    POSITIVE LOGITS
    ven
    0.33
     bis
    0.26
    _Generic
    0.26
    clude
    0.26
    DrawerToggle
    0.25
    æ¯ĶèµĽ
    0.25
     bic
    0.24
    ISR
    0.24
     failure
    0.24
    ä¸Ģ声
    0.24
    Activations Density 0.046%

    No Known Activations